Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0448. Min Range: -7.0448
Max Act: 7.0448. Min Act: -0.1700
Data Index: 7684820 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.8886. Min Act: -0.1700
Data Index: 3883693 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.8573. Min Act: -0.1700
Data Index: 7155207 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.8261. Min Act: -0.1700
Data Index: 696915 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7948. Min Act: -0.1700
Data Index: 821032 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7948. Min Act: -0.1700
Data Index: 363144 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7323. Min Act: -0.1700
Data Index: 1217041 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5177781 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7636. Min Act: -0.1700
Data Index: 7024619 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7636. Min Act: -0.1700
Data Index: 4189232 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7323. Min Act: -0.1700
Data Index: 4499015 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7323. Min Act: -0.1700
Data Index: 4553702 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.6386. Min Act: -0.1700
Data Index: 7510276 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.7011. Min Act: -0.1700
Data Index: 5261114 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.6698. Min Act: -0.1700
Data Index: 6487627 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.6698. Min Act: -0.1700
Data Index: 363145 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.6386. Min Act: -0.1700
Data Index: 4718702 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.6386. Min Act: -0.1700
Data Index: 8004536 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.5761. Min Act: -0.1700
Data Index: 5398515 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0448. Min Range: -7.0448
Max Act: 6.5448. Min Act: -0.1700
Data Index: 5261112 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19